STransE: a novel embedding model of entities and relationships in knowledge bases

TL;DR

STransE is a new embedding model that improves link prediction in knowledge bases by combining previous models, representing entities as vectors and relations with matrices and translation vectors, outperforming existing models.

Contribution

It introduces STransE, a novel embedding model that combines SE and TransE, achieving better link prediction performance and establishing a new baseline.

Findings

Outperforms previous models on benchmark datasets

Provides a simple yet effective combination of existing approaches

Serves as a new baseline for future link prediction models

Abstract

Knowledge bases of real-world facts about entities and their relationships are useful resources for a variety of natural language processing tasks. However, because knowledge bases are typically incomplete, it is useful to be able to perform link prediction or knowledge base completion, i.e., predict whether a relationship not in the knowledge base is likely to be true. This paper combines insights from several previous link prediction models into a new embedding model STransE that represents each entity as a low-dimensional vector, and each relation by two matrices and a translation vector. STransE is a simple combination of the SE and TransE models, but it obtains better link prediction performance on two benchmark datasets than previous embedding models. Thus, STransE can serve as a new baseline for the more complex models in the link prediction task.